Qwen3 Next 80B A3B Thinking
Specifications
- Input
- Output
- Context window
- 262K tokens
- Released
- Sep 2025
Performance
- Speed
- 54 t/s
- TTFT
- 319 ms
- Latency
- —
- Intelligence
- —
Pricing
- Input
- €0.19 per 1M tokens
- Output
- €1.50 per 1M tokens
About this model
Qwen's "thinking-optimized" 80B model designed for sustained multi-step reasoning, structured deliberation, and high-precision problem-solving across math, code, and complex planning tasks.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Default on
Knowledge horizon
Released Sep 2025
Today
Since release 8 mo
See also
Add Model to Comparison
Search for a model to add